Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Forms of "to be"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conson
    -0.07
     điều
    -0.06
     iddia
    -0.06
    ToStr
    -0.06
    Destructor
    -0.06
    тивного
    -0.06
     dolphin
    -0.06
    APON
    -0.06
    reat
    -0.05
    Spell
    -0.05
    POSITIVE LOGITS
     forgot
    0.07
     Among
    0.07
    /about
    0.07
     bande
    0.06
    、↵
    0.06
    *(
    0.06
    아요
    0.06
    .case
    0.06
     &&
↵
    0.06
         
↵
    0.06
    Act Density 0.065%

    No Known Activations